Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →worldwonderer/video-assemble
合成视频解说最终成片：把旁白音频铺到源视频上，按旁白窗口压低原声，生成 SRT / ASS 字幕并可烧录， 最后做响度标准化。作为最终合成阶段使用。输入源视频、tts_meta.json 与旁白位置； 输出 recap 成片和字幕。触发词：视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。
Passed 15 of 19 test cases with the skill, and 3 of 19 without it.
and 18 more in the full report
14 fixed3 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am running repeated test builds of video assembly in my pipeline. Instead of generating timestamped output files that clutter the working directory, what fixed filename alias is overwritten on every run?
| Checked | Without skill | With skill |
|---|---|---|
| Overwrites recap_<stem>.mp4 as the fixed final output alias on each run. | Missed | Passed |
The instructions your model reads when the skill loads.
本技能负责最终合成：
subtitles.srt；默认同时生成并烧录 subtitles.ass，--no-burn-subtitles 可关闭。合成阶段只实现创作决定，不凭空制造决定。Agent 在写旁白位置前，已在 visual_audio_board.json 为每个 beat 指定 audio_owner：
original_dialogueaction_soundambience / musicsilencenarration因此，旁白间隙是主动选择，不是必须填满的空白。不要为了“更满”而加入通用 BGM、压住必须听见的台词或消除有意义的沉默。
当前渲染器不解析 visual_audio_board.json；Agent 通过旁白时间、overlaps_speech、原声留白与现有混音参数落实这些决定。
<video>：源视频；cut 模式下为 edited_source.mp4。work_dir/tts_meta.json：配音阶段写出的 {segments: [...]}。每段包含 audio_path、时间、pause_after_ms、overlaps_speech 和用于混音/字幕的位置。下面的 scripts/... 均相对于本技能目录。若执行器从仓库根目录启动，请给脚本路径加上本技能的绝对目录。脚本不从其他技能目录读取文件；外部输入仅限命令显式传入的视频、参数与 work_dir 产物。
python3 scripts/assemble.py <video> --work-dir <work_dir> \
[--recap-stem <name>] [--output-dir <dir>] [--no-burn-subtitles] \
[--subtitle-y-top <inclusive-y> --subtitle-y-bot <exclusive-y>] \
[--source-video <orig.mp4>] [--export-jianying [--jianying-out <dir>]]
test cases passed, vs 3 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.